© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 16503
    Prev
    Next
    INDEX
    Explanations

    words related to proper nouns or names

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NATO
    -0.70
     vert
    -0.66
     eurozone
    -0.64
    UE
    -0.62
     sign
    -0.62
     helium
    -0.62
     makeup
    -0.61
     Nato
    -0.60
     reserve
    -0.59
     Wings
    -0.59
    POSITIVE LOGITS
    har
    4.47
    Har
    1.77
    hari
    1.61
    hur
    1.56
    han
    1.52
    hat
    1.44
    hun
    1.35
    kar
    1.32
    haw
    1.31
     Har
    1.27
    Activations Density 0.005%

    No Known Activations